Image Segmentation for Graphene Images

By Joshua A Schiller

University of Illinois at Urbana-Champaign, Urbana, IL

Published on

Abstract

This lecture reviews various clustering algorithms and how Gr-ResQ plans to use them for segmenting SEM images. The lecture outlines the need for a fast, automated means for identifying regions of images corresponding to graphene. Simple methods, like color masking and template matching, are discussed initially. Unsupervised clustering methods are then introduced as potential improvements. Finally, the lecture reviews the utility of artificial neural networks for classifying pixels. Throughout the presentation, the strengths and weaknesses of different techniques is reviewed as is their relation to the structure of the data.

Cite this work

Researchers should cite this work as follows:

  • Joshua A Schiller (2020), "Image Segmentation for Graphene Images," https://nanohub.org/resources/33342.

    BibTex | EndNote

Time

Location

University of Illinois at Urbana-Champaign, Urbana, IL

Tags